maxpark Goto Github PK

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

mat-cnn-sopc

MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip

maxconvnet

https://github.com/rjkris/cifar10-HLS

meloppr

miemiedetection

Pytorch implementation of YOLOX、PPYOLO、PPYOLOv2、FCOS an so on.

minigo

An open-source implementation of the AlphaGoZero algorithm

mipi_csi2_tx

VHDL code for using Xilinx MGT gigabit transceivers/LVDS lines for MIPI CSI-2 TX protocol

ml-design-patterns

O'Reilly <머신러닝 디자인 패턴 Machine Learning Design Patterns> 소스코드 저장소

ml-mnist-caffe

This tutorial shows how to train from scratch LeNet CNN with the MNIST dataset and then implement it on ZCU102 board with Xilinx DNNDK 2.0.8 release tools

ml-suite

Getting Started with Xilinx ML Suite

mljar-supervised

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

mlops

MLOps examples

mlops-ocr

MLOps for OCR

mmdeploy

OpenMMLab Model Deployment Framework

mmdetection-to-tensorrt

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox

mnist_accelerator

Accelerating CNN in hardware aspect

mnist_center_loss_pytorch

A PyTorch implementation of center loss on MNIST

mnist_hls

mnn

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

mobilenet-yolo

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:

monk_gui

A Graphical user Interface for deep learning and computer vision over Monk Libraries

mosse-xoh

In this project a hardware-software implementation of adaptive correlation filter tracking for a 3840 x 2160 @ 60 fps video stream in a Zynq UltraScale+ MPSoC is discussed. Correlation filters gained popularity in recent years because of their efficiency and good results in the VOT (Visual Object Tracking) challenge. An implementation of the MOSSE (Minimum Output Sum of Squared Error) algorithm is presented. It utilizes 2-dimensional FFT for computing correlation and updates filter coefficients in every frame. The initial filter coefficients are computed on the ARM processor in the PS (Processing System), while all other operations are preformed in PL (Programmable Logic). The presented architecture was described with the use of Verilog hardware description language.

multiscale-template-matching

Match a cropped image to the original image with an efficient algorithm using Python and OpenCV.

mvtec_ad-anomaly-detection

The solutions for the dacon competition (1st place).

myir-imx-linux

Linux kernel source for i.MX serials boards of MYiR Electronics.

naslib

NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.

neon_samples

Neon capture and inference sample with Python and C++ language

netron

Visualizer for neural network, deep learning, and machine learning models

netspresso-compressiontoolkit-modelzoo

Model Zoo for NetsPresso Compression Toolkit